- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oaustegard/claude-skills --skill browsing-bluesky -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oaustegard/claude-skills --skill browsing-bluesky -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oaustegard/claude-skills --skill browsing-bluesky -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oaustegard/claude-skills --skill browsing-bluesky -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/oaustegard/claude-skills/tree/HEAD/browsing-bluesky來自發布者
Access Bluesky content through public APIs and real-time firehose. Supports optional authentication for personalized feeds. Includes account analysis for categorization.
Add skill directory to path and import:
import sys
sys.path.insert(0, '/path/to/skills/browsing-bluesky') # or use .claude/skills symlink path
from browsing_bluesky import (
# Core browsing
search_posts, get_user_posts, get_profile, get_feed_posts, sample_firehose,
get_thread, get_quotes, get_likes, get_reposts,
get_followers, get_following, search_users,
# Trending
get_trending, get_trending_topics,
# Account analysis
get_all_following, get_all_followers, extract_post_text,
extract_keywords, analyze_account, analyze_accounts,
# Authentication utilities
is_authenticated, get_authenticated_user, authenticated_identity,
clear_session
)
Authentication enables personalized feeds (like Paper Skygest) that require knowing who's asking.
export BSKY_HANDLE="yourhandle.bsky.social"
export BSKY_APP_PASSWORD="xxxx-xxxx-xxxx-xxxx"
Two credential pairs are recognised, and the prefix is the only difference:
BSKY_IDENTITY=muninn|owner picks one outright, and a pair named that way is
never substituted for: asking for muninn with no Muninn pair set reads as
public rather than quietly reading as the owner. An unrecognised value raises.
This matters because a booted container holds both pairs. Until
2026-08-28 the unprefixed one won, so every authenticated read — the following
timeline, and the mutes, blocks and labelers that shape all of them — came back
as the account owner with nothing in the output saying so, from a skill
documented as read-only that was nonetheless holding an app password carrying
write scope on his account. On a machine with only the documented BSKY_*
pair, nothing changes.
BSKY_IDENTITY is configuration, not auth failure, and raises insteadif is_authenticated():
print(f"Logged in as: {get_authenticated_user()}")
else:
print("Using public access")
# Which pair answered — a handle alone does not say whether it was chosen
# or simply the only one set.
authenticated_identity() # {'identity': 'muninn', 'handle': ..., 'did': ...}
# Clear session if needed (e.g., switching accounts or identities)
clear_session()
Use search_posts() with query syntax matching bsky.app advanced search:
event sourcing"event sourcing"from:acairns.co.uk or use author= paramsince:2025-01-01 or use since= param#python mentions:user domain:github.comCombine query syntax with function params for complex searches.
get_profile(handle) for context (bio, follower count, post count)get_user_posts(handle, limit=N)search_posts(query, author=handle)Recommended workflow — trending API first, firehose for deep dives:
topics = get_trending_topics(limit=10)
# Returns: {topics: [{topic, display_name, description, link}, ...],
# suggested: [...]}
trends = get_trending(limit=10)
for t in trends:
print(f"{t['display_name']} — {t['post_count']} posts ({t['status']})")
# Each trend includes: topic, display_name, link, started_at,
# post_count, status, category, actors
posts = search_posts(trend["topic"], limit=25)
Prerequisites: Install Node.js dependencies once per session:
cd /home/claude && npm install ws https-proxy-agent 2>/dev/null
data = sample_firehose(duration=30) # Full firehose sample
data = sample_firehose(duration=20, filter="python") # Filtered sample
Returns dict with keys:
{startTime, endTime, durationSeconds} — sampling time range{totalReceived, totalPosts, postsPerSecond, filter, languages} — volume metrics and language breakdown[[word, count], ...] — top 50 words (count >= 3)[[bigram, count], ...] — top 30 bigrams (count >= 2)[[trigram, count], ...] — top 20 trigrams (count >= 2)[[entity, count], ...] — top 25 handles/hashtags (count >= 2)[{text, altTexts, hasImages}, ...] — first 50 matching postsget_feed_posts() accepts:
https://bsky.app/profile/austegard.com/lists/3lankcdrlip2fhttps://bsky.app/profile/did:plc:xxx/feed/feednameat://did:plc:xxx/app.bsky.graph.list/xyzThe function extracts the AT-URI from URLs automatically.
Fetch full thread context for a post with parents and replies:
thread = get_thread("https://bsky.app/profile/user/post/xyz", depth=10)
# Returns: {post: {...}, parent: {...}, replies: [...]}
Discover posts that quote a specific post:
quotes = get_quotes("https://bsky.app/profile/user/post/xyz")
for q in quotes:
print(f"@{q['author_handle']}: {q['text'][:80]}")
Get users who engaged with a post:
likes = get_likes(post_url)
reposts = get_reposts(post_url)
# Accepts both URLs and AT-URIs
likes = get_likes("at://did:plc:.../app.bsky.feed.post/...")
Every parsed post carries an images field — a list of
{alt, url, transcription} dicts, one per embed image. The legacy
image_alts: list[str] field is preserved (non-empty alts only).
When alt text is missing and the image content matters, opt in to model
transcription via the transcribe parameter on any post-fetch function
(get_user_posts, search_posts, get_feed_posts, get_thread,
get_quotes):
# Routine/bulk work (zeitgeist, inbox review, news scans) —
# gemini-2.5-flash-lite is the recommended default. Cheapest production
# model anywhere ($0.10/$0.40 per 1M tokens), ~95% accuracy on dense
# screenshots in May 2026 benchmarks:
posts = get_user_posts("ayourtch.bsky.social", limit=40, transcribe="gemini-lite")
# Token-perfect transcription, still cheap:
posts = get_user_posts(..., transcribe="gemini-flash")
# Frontier model with thinking_level=minimal — for cases where the image
# content needs reasoning, not just transcription:
posts = get_user_posts(..., transcribe="gemini-3.5-flash")
# Anthropic single-vendor option (note: empirically weaker prompt-following
# than Gemini on dense transcription — Haiku tends to summarize rather
# than transcribe):
posts = get_user_posts(..., transcribe="haiku")
# Interactive sessions where image is part of the active task and you want
# conversation context to inform interpretation (only available on Anthropic):
thread = get_thread(post_url, transcribe="opus")
# Default (no transcription) — current behavior preserved:
posts = get_user_posts("ayourtch.bsky.social", limit=40)
Policy is invariant across all callers: images with non-empty alt text are
never transcribed (the author already described the image; trust it).
Only images with missing or empty alt are sent to the model. Network or
API failures leave transcription as None; callers degrade silently.
Cost/quality empirics (May 2026, n=3 dense terminal screenshots, single run each — sample size is small, treat as directional):
The haiku and opus rows were measured on Haiku 4.5 and Opus 4.7. The aliases now
resolve to claude-haiku-5-5 and claude-opus-5-5; those rows have not been re-measured.
Requires either ANTHROPIC_API_KEY (or API_KEY in /mnt/project/claude.env)
for the haiku / opus aliases, or CF AI Gateway credentials in
/mnt/project/proxy.env for the gemini-* aliases. Transcription only
fires when the parameter is set, so callers without the relevant
credentials can simply pick a different alias or leave the feature off.
Navigate follower/following relationships:
followers = get_followers("handle.bsky.social")
following = get_following("handle.bsky.social")
# Returns list of actor dicts with handle, display_name, did, description, etc.
Search for users by name, handle, or bio:
users = search_users("machine learning researcher")
for u in users:
print(f"{u['display_name']} (@{u['handle']}): {u['description'][:100]}")
https://api.bsky.app/xrpc/ for unauthenticated readshttps://bsky.social/xrpc/ for authenticated requestsapp.bsky.unspecced.getTrends (rich) and app.bsky.unspecced.getTrendingTopics (lightweight)wss://jetstream1.us-east.bsky.network/subscribeAll API functions return structured dicts with:
uri: AT protocol identifiertext: Post contentcreated_at: ISO timestampauthor_handle: User handleauthor_name: Display namelikes, reposts, replies: Engagement countslinks: Full URLs extracted from post facets (post text truncates URLs with "...")image_alts: Alt text from embedded imagesurl: Direct link to post on bsky.appProfile function returns: handle, display_name, description, followers, following, posts, did
Analyze accounts for categorization by topic. Fetches profile and posts, extracts keywords, and returns structured data for Claude to categorize.
# Analyze accounts you follow
results = analyze_accounts(following="yourhandle.bsky.social", limit=50)
# Analyze your followers
results = analyze_accounts(followers="yourhandle.bsky.social", limit=50)
# Analyze specific handles
results = analyze_accounts(handles=["user1.bsky.social", "user2.bsky.social"])
analysis = analyze_account("user.bsky.social")
# Returns: {handle, display_name, description, keywords, post_count, followers, following}
Stopwords parameter filters domain-specific noise:
"en": English (general purpose, default)"ai": AI/ML domain (filters tech boilerplate)"ls": Life Sciences (filters research methodology)results = analyze_accounts(following="handle", stopwords="ai")
Requires: extracting-keywords skill with YAKE venv for keyword extraction.
results = analyze_accounts(
following="handle",
exclude_patterns=["bot", "spam", "promo"] # Skip accounts matching these
)
For large account lists beyond the 100 limit of get_following/get_followers:
all_following = get_all_following("handle", limit=500) # Handles pagination
all_followers = get_all_followers("handle", limit=500)
Each analyzed account returns:
{
"handle": "user.bsky.social",
"display_name": "User Name",
"description": "Bio text here",
"keywords": ["keyword1", "keyword2", "keyword3"],
"post_count": 20,
"followers": 1234,
"following": 567
}
Claude uses bio + keywords to categorize accounts by topic without hardcoded rules
Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and lists, analyze and categorize accounts. Supports authenticated access for person
---name: browsing-blueskydescription: Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read…---# browsing-bluesky/SKILL.md總覽
Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and lists, analyze and categorize accounts. Supports authenticated access for personalized feeds. Use for Bluesky research, user monitoring, trend analysis, feed reading, firehose sampling, account categorization.
常見問題
從發布者下載 browsing-bluesky/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/oaustegard/claude-skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。